© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149158
    Prev
    Next
    INDEX
    Explanations

    without compensating

    np_acts-logits-general · gemini-2.5-flash-lite

    ** (bold) and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atthanam
    0.52
    atán
    0.49
    ㍉
    0.49
    itih
    0.48
     व्हाट
    0.48
    ästä
    0.48
    ဆုံး
    0.48
    genCode
    0.46
    avacan
    0.46
     정의역
    0.46
    POSITIVE LOGITS
    c
    0.48
    Good
    0.46
    ك
    0.46
    發展
    0.45
     North
    0.44
    North
    0.44
    的发展
    0.43
     Quem
    0.43
     Gute
    0.43
    Quem
    0.42
    Activations Density 0.001%

    No Known Activations